Layout consistent segmentation of 3-D meshes via conditional random fields and spatial ordering constraints

Authors:
Alexander Zouhar;Sajjad Baloch;Yanghai Tsin;Tong Fang;Siegfried Fuchs
Affiliations:
Siemens Corporate Research, Inc., Princeton and Dresden University of Technology, Dresden, Germany;Siemens Corporate Research, Inc., Princeton;Siemens Corporate Research, Inc., Princeton;Siemens Corporate Research, Inc., Princeton;Dresden University of Technology, Dresden, Germany
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
Year:
2010

Citing 8
Cited 0

Fast Approximate Energy Minimization via Graph Cuts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
What Energy Functions Can Be Minimizedvia Graph Cuts?

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast exact and approximate geodesics on meshes

ACM SIGGRAPH 2005 Papers
Design and Performance of a Fault-Tolerant Real-Time CORBA Event Service

ECRTS '06 Proceedings of the 18th Euromicro Conference on Real-Time Systems
Consistent mesh partitioning and skeletonisation using the shape diameter function

The Visual Computer: International Journal of Computer Graphics
Randomized cuts for 3D mesh analysis

ACM SIGGRAPH Asia 2008 papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

We address the problem of 3-D Mesh segmentation for categories of objects with known part structure. Part labels are derived from a semantic interpretation of non-overlapping subsurfaces. Our approach models the label distribution using a Conditional Random Field (CRF) that imposes constraints on the relative spatial arrangement of neighboring labels, thereby ensuring semantic consistency. To this end, each label variable is associated with a rich shape descriptor that is intrinsic to the surface. Randomized decision trees and cross validation are employed for learning the model, which is eventually applied using graph cuts. The method is flexible enough for segmenting even geometrically less structured regions and is robust to local and global shape variations.